A comparative evaluation of search techniques for query‐by‐humming using the MUSART testbed

Abstract

Query-by-Humming systems offer content-based searching for melodies and require no special musical training or knowledge. Many such systems have been built, but there has not been much useful evaluation and comparison in the literature due to the lack of shared databases and queries. The MUSART project testbed allows various search algorithms to be compared using a shared framework that automatically runs experiments and summarizes results. Using this testbed, we compared algorithms based on string alignment, melodic contour matching, a hidden Markov model, n-grams, and CubyHum. Retrieval performance is very sensitive to distance functions and the representation of pitch and rhythm, which raises questions about some previously published conclusions. Some algorithms are particularly sensitive to the quality of queries. Our queries, which are taken from human subjects in a fairly realistic setting, are quite difficult, especially for n-gram models. Finally, simulations on query-byhumming performance as a function of database size indicate that retrieval performance falls only slowly as the database size increases.

Audio Cover Song Identification and Similarity: Background, Approaches, Evaluation, and Beyond

“…Within these, research done in areas such as query-by-humming systems, content-based music retrieval, genre classification, or audio fingerprinting, is relevant for addressing cover song similarity. Many ideas for cover song identification systems come from the symbolic domain [45,56,67,81], and query-by-humming systems [12] are paradigmatic examples. In query-by-humming systems, the user sings or hums a melody and the system searches for matches in a musical database.…”

“…This way, a key-independent feature sequence is obtained [2,43,68]. This idea, which is grounded in existing research on symbolic music processing [12,45,56,67,81], has been recently extended to PCP sequences [40,38] by using the concept of optimal (or minimizing) transposition indices [52,76].…”

“…This strategy is employed in query-by-humming systems [12] and, combined with relative pitch encoding (section 2.3), leads to a representation that is key and tempo independent. However, for the reasons outlined in section 2.1, extracting a symbolic descriptor sequence is not straightforward and may lead to important estimation errors.…”

An Improved Melody Contour Feature Extraction for Query by Humming

“…Then melodic representation will be analyzed by above technique. N-grams is another approach, which is widely used in text retrieval and applied to retrieve songs in music system [4], [14], [15], [16]. It is particularly effective for short queries and manual queries not for automatic queries [17].…”

“…It is particularly effective for short queries and manual queries not for automatic queries [17]. In [14] considered the use of above method as a front end in a two-stage search in which a fast indexing algorithm based on n-grams narrows the search. In addition, string matching based on statistical models including Hidden Markov Models (HMMs) in [14], [18], [19].…”